add transcript id to annotated xml output

cmat/output_generation/annotated_clinvar.py

@@ -91,7 +91,6 @@ def annotate(self, record):
             self.overall_counts['both_measure_and_trait'] += 1
 
     def annotate_and_count_measure(self, record):
-        # TODO include transcript if present in variant_to_gene_mappings
         consequence_types, variant_category = get_consequence_types(record.measure, self.variant_to_gene_mappings)
         record.measure.add_ensembl_annotations(consequence_types)
 
@@ -242,8 +241,14 @@ def add_ensembl_annotations(self, consequences):
             attribute_elt.text = consequence_attributes.so_term.so_name.replace('_', ' ')
             so_elt = ET.Element('XRef', attrib={'ID': self.format_so_term(consequence_attributes.so_term),
                                                 'DB': 'Sequence Ontology'})
-            ensembl_elt = ET.Element('XRef', attrib={'ID': consequence_attributes.ensembl_gene_id, 'DB': 'Ensembl'})
-            attr_set_elt.extend((attribute_elt, so_elt, ensembl_elt))
+            ensembl_gene_elt = ET.Element('XRef', attrib={'ID': consequence_attributes.ensembl_gene_id,
+                                                          'DB': 'Ensembl Gene'})
+            attr_set_elt.extend((attribute_elt, so_elt, ensembl_gene_elt))
+            # Add transcript if present
+            if consequence_attributes.ensembl_transcript_id:
+                ensembl_transcript_elt = ET.Element('XRef', attrib={'ID': consequence_attributes.ensembl_transcript_id,
+                                                                    'DB': 'Ensembl Transcript'})
+                attr_set_elt.append(ensembl_transcript_elt)
             consequence_elts.append(attr_set_elt)
         self.measure_xml.extend(consequence_elts)
 

cmat/output_generation/consequence_type.py

@@ -10,15 +10,14 @@
 logger = logging.getLogger(__package__)
 
 
-def process_gene(consequence_type_dict, variant_id, ensembl_gene_id, so_term):
-    consequence_type_dict[variant_id].append(ConsequenceType(ensembl_gene_id, SoTerm(so_term)))
+def process_gene(consequence_type_dict, variant_id, ensembl_gene_id, so_term, ensembl_transcript_id=None):
+    consequence_type_dict[variant_id].append(ConsequenceType(ensembl_gene_id, SoTerm(so_term), ensembl_transcript_id))
 
 
 def process_consequence_type_file(snp_2_gene_file, consequence_type_dict=None):
-    # TODO adapt for transcripts if present
     """
     Return a dictionary of consequence information extracted from the given file.
-    If consequence_type_dict is provided then the information will be merge into this dictionary.
+    If consequence_type_dict is provided then the information will be merged into this dictionary.
     """
     logger.info('Loading mapping rs -> ENSG/SOterms')
     if consequence_type_dict is None:
@@ -41,7 +40,12 @@ def process_consequence_type_file(snp_2_gene_file, consequence_type_dict=None):
                 logger.warning('Skip line with missing gene ID: {}'.format(line))
                 continue
 
-            process_gene(consequence_type_dict, variant_id, ensembl_gene_id, so_term)
+            # Include transcript if present
+            if len(line_list) >= 5:
+                ensembl_transcript_id = line_list[4]
+                process_gene(consequence_type_dict, variant_id, ensembl_gene_id, so_term, ensembl_transcript_id)
+            else:
+                process_gene(consequence_type_dict, variant_id, ensembl_gene_id, so_term)
 
     logger.info('{} rs->ENSG/SOterms mappings loaded'.format(len(consequence_type_dict)))
     return consequence_type_dict
@@ -112,9 +116,10 @@ class ConsequenceType:
     with relationship to ensembl gene IDs and SO terms
     """
 
-    def __init__(self, ensembl_gene_id, so_term):
+    def __init__(self, ensembl_gene_id, so_term, ensembl_transcript_id=None):
         self.ensembl_gene_id = ensembl_gene_id
         self.so_term = so_term
+        self.ensembl_transcript_id = ensembl_transcript_id
 
     def __eq__(self, other):
         return isinstance(other, self.__class__) and self.__dict__ == other.__dict__